Statistical and optimization methods to expedite neural network training for transient identification
- Argonne National Lab., IL (United States). Reactor Analysis Div.
- Universidad Nacional Autonoma de Mexico, Mexico City (Mexico). Inst. de Ciencias Nucleares
- Michigan Univ., Ann Arbor, MI (United States). Dept. of Nuclear Engineering
Two complementary methods, statistical feature selection and nonlinear optimization through conjugate gradients, are used to expedite feedforward neural network training. Statistical feature selection techniques in the form of linear correlation coefficients and information-theoretic entropy are used to eliminate redundant and non-informative plant parameters to reduce the size of the network. The method of conjugate gradients is used to accelerate the network training convergence and to systematically calculate the Teaming and momentum constants at each iteration. The proposed techniques are compared with the backpropagation algorithm using the entire set of plant parameters in the training of neural networks to identify transients simulated with the Midland Nuclear Power Plant Unit 2 simulator. By using 25% of the plant parameters and the conjugate gradients, a 30-fold reduction in CPU time was obtained without degrading the diagnostic ability of the network.
- Research Organization:
- Argonne National Lab., IL (United States). Reactor Analysis Div.
- Sponsoring Organization:
- USDOE; USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-31109-ENG-38
- OSTI ID:
- 6587226
- Report Number(s):
- ANL/RA/CP-77255; CONF-930401-12; ON: DE93009985
- Resource Relation:
- Conference: Meeting on nuclear plant instrumentation, control and man-machine interface technologies, Oak Ridge, TN (United States), 18-21 Apr 1993
- Country of Publication:
- United States
- Language:
- English
Similar Records
Artificial Neural Network Training with Conjugate Gradients for Diagnosing Transients in Nuclear Power Plants
Accelerating learning of neural networks with conjugate gradients for nuclear power plant applications
Related Subjects
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
NEURAL NETWORKS
TRAINING
NUCLEAR POWER PLANTS
ALGORITHMS
CONVERGENCE
NONLINEAR PROBLEMS
OPTIMIZATION
STATISTICAL MODELS
TRANSIENTS
EDUCATION
MATHEMATICAL LOGIC
MATHEMATICAL MODELS
NUCLEAR FACILITIES
POWER PLANTS
THERMAL POWER PLANTS
220900* - Nuclear Reactor Technology- Reactor Safety
990200 - Mathematics & Computers